arXiv cs.MA· Xinxing Ren, Qianbo Zang, Ziyan Wang, Suman Deb, Qiang Yang, Caelum Forder, Peter Carroll, Gilead Gevero, Jing Liu, Yali Du, Milind Tambe, Zekun Guo·· 12 小时前AI 评分55
Coral Discovery：自主研究中的认知分工机制
Coral Discovery: The Division of Cognitive Labor in Autonomous Research
AI 导读
论文提出 Coral Discovery，用方向板为 LLM 智能体的每次尝试标注方向和具体方法，按方向追踪评测收益、给少尝试方向加探索奖励，并建议各方向应分配的智能体数量。
正文
Authors:Xinxing Ren, Qianbo Zang, Ziyan Wang, Suman Deb, Qiang Yang, Caelum Forder, Peter Carroll, Gilead Gevero, Jing Liu, Yali Du, Milind Tambe, Zekun Guo
Abstract:A research community is only as strong as the way it divides its cognitive labour. The philosopher Philip Kitcher argued that researchers should not all pursue the most promising approach. Credit rules, not a central plan, keep some of them on other lines. We bring this question to autonomous research, where Large Language Model agents improve programs against a deterministic grader. Agents that share only a score follow the leader and converge onto one approach. Coral Discovery gives the community a direction board. A verifier labels every attempt with a direction, the mechanism earning the score, and a method, one change within it. Per direction, the board tracks how much each eval improves the score, adds an exploration bonus for little-tried directions, prices the option of opening a new direction, and suggests how many agents each direction deserves. Credit is earned against a direction's own best, so a lagging direction keeps its agents. Agents finish their lines, then treat the board as advice. We test on nine tasks with the same model and budget, without grader access except for Kernel. Coral Discovery beats the strongest open autonomous multi-agent system on 6 tasks, ties on 1, and loses on 2. Against published numbers, it is best or tied on 4. It improves the reported Kernel result from 1103 to 1095 cycles and passes 1103 at eval 275, under half of the 596 used before. It sets a new Polyominoes state of the art, 91.78 against 87.0. Direction labels show that the leading scores rest on directions a score-only community never entered. Code will be released shortly.
| Subjects: | Multiagent Systems (cs.MA) |
| Cite as: | arXiv:2610.33281 [cs.MA] |
| (or arXiv:2610.33281v1 [cs.MA] for this version) | |
| https://doi.org/10.48550/arXiv.2610.33281 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Zekun Guo [view email]
[v1]
Fri, 23 Oct 2026 20:46:11 UTC (1,599 KB)
来源：arXiv cs.MA · arxiv.org